Japan Tsunami Warnings

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate read-only, idempotent, open-world, non-destructive, so no contradiction. The description adds valuable behavioral context: the warning lifecycle and inclusion of cancelled bulletins for audit trails. These are beyond annotations and help the agent understand the data's temporal nature.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the core purpose and data fields, then covers coverage, lifecycle, and use case. It's focused without excessive detail, but the coverage sentence is a bit redundant with the description of coastal areas. Still, it's well-structured for quick reading.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema exists (not shown here, but indicated), so return values are presumably documented elsewhere. The description covers the tool's domain, data source, usage, and lifecycle. It lacks explicit mention of time window or default sorting behavior, but given the schema includes pagination and order, this is sufficient. Overall, an agent can determine when to use it and what to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for all three parameters (limit, order, offset), so baseline is 3. The description doesn't explicitly explain each parameter, but the schema already does. However, the description's mention of pagination and sorting context is implicit, and the schema descriptions are self-explanatory. A slight bonus for the description hinting at 'recent' but not fully, so a 4 is generous but acceptable given schema clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves tsunami warning/advisory bulletins from JMA via P2PQuake, and enumerates specific data fields (warning grade, immediate-danger flag, wave height, arrival time, earthquake details). It differentiates from siblings like p2pquake.seismic.recent_quakes and p2pquake.seismic.quake_history by focusing on tsunami warnings and the lifecycle (FirstReport → Update → AllClear).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the tool is for real-time tsunami monitoring in Japan and lists coverage areas. It distinguishes from general earthquake tools by specifying it returns warnings/advisories, not just seismic events. It also notes that cancelled bulletins are included, which sets expectations for audit use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.